staging

Nova Agent Utility Network: MCP utility for autonomous agents.

CommunityOnlineNo sign-inGlobalFreeRead-only

What it can do

  • Web Fetch Clean: WHEN: Need cleaned public page (title + Markdown) without a browser. OUTPUT: title, markdown, finalUrl, retrievalTimeMs. LIMITATION: STANDARD HTTP only; no browser/JS render/PREMIUM/R
  • Web Extract Json: WHEN: Need schema-shaped fields from a public page (often after web_fetch_clean). OUTPUT: data + fields_not_found (+ routing/hash metadata). LIMITATION: Deterministic E1 only; never
  • Change Detect: WHEN: On-demand check whether a URL fingerprint changed since a prior observation (caller schedules repeats). OUTPUT: changed, material, observation_id, delta, finalUrl, timestamp. LIMI

What data it sees

Do you need an account

No: the server works without sign-in

Nova Agent Utility Network: MCP utility for autonomous agents. STAGING/TESTNET pay-per-use utilities on Base Sepolia via x402. Not commercial/mainnet.

How to connect

How to connect staging to Claude

The server address to paste into Claude settings:

https://staging--naun.run.tools

  1. Open Claude (claude.ai or the desktop app).
  2. Go to Settings → Connectors.
  3. Click Add custom connector.
  4. Paste the server address copied below into Remote MCP server URL and click Add.
  5. In a chat, click + → Connectors and switch the new connector on.

Custom connectors are available on Free, Pro, Max, Team and Enterprise plans (Free is limited to one). On Team and Enterprise an organization Owner adds the connector first under Organization settings → Connectors.

Authorization

After you click Add, a sign-in window for the service opens. Sign in with your own account and approve access. Claude never sees your password.

How to connect staging to ChatGPT

The server address to paste into ChatGPT settings:

https://staging--naun.run.tools

  1. Open ChatGPT in a browser (chatgpt.com). A Plus, Pro, Business, Enterprise or Edu plan is required.
  2. Turn on developer mode once: Settings → Apps → Advanced settings → Developer mode.
  3. Open Settings → Connectors and click Create.
  4. Fill in the form: Name (anything), Description (one line about what the service does), MCP server URL (copy it below).
  5. Under Authentication choose OAuth if the service requires sign-in, otherwise None. Click Create.
  6. In a new chat open + → Apps/Connectors and enable the connector.

OpenAI has renamed this section before (Connectors → Apps/Plugins). If the label differs, search settings for "developer mode". On Business/Enterprise workspaces an admin must allow custom connectors first.

Authorization

On first use ChatGPT opens the service's sign-in window. Sign in and approve access.

How to connect staging to Cursor

The server address to paste into Cursor settings:

https://staging--naun.run.tools

Fastest: click Open in Cursor below and confirm the prompt.

Manually:

  1. In Cursor open Settings → Cursor Settings → MCP and click Add new global MCP server.
  2. Paste the JSON copied below into ~/.cursor/mcp.json (per project: .cursor/mcp.json in the repo root).
  3. Save the file. The server appears in the MCP list; authorize it there if asked.

Authorization

If the service needs sign-in, an authorize button appears next to the server in the MCP list.

Server tool list (5)

Raw names from tools/list. Only developers need these.

web_fetch_cleanWHEN: Need cleaned public page (title + Markdown) without a browser. OUTPUT: title, markdown, finalUrl, retrievalTimeMs. LIMITATION: STANDARD HTTP only; no browser/JS render/PREMIUM/RENDERED; JS-heavy = best-effort SSR/HTML. PRICE: $0.003 USDC (Base Sepolia) via x402 per successful call. TESTNET/STAGING. Next (suggestion only, never auto-invoked): web_extract_json → change_detect.
web_extract_jsonWHEN: Need schema-shaped fields from a public page (often after web_fetch_clean). OUTPUT: data + fields_not_found (+ routing/hash metadata). LIMITATION: Deterministic E1 only; never fabricates; not browser fidelity; structured_data_rich not guaranteed. PRICE: $0.008 USDC (Base Sepolia) via x402 per successful call. TESTNET/STAGING. Next (suggestion only, never auto-invoked): refine schema / web_fetch_clean inspect → change_detect.
change_detectWHEN: On-demand check whether a URL fingerprint changed since a prior observation (caller schedules repeats). OUTPUT: changed, material, observation_id, delta, finalUrl, timestamp. LIMITATION: Not a polling SKU; not visual AI; live fetch each observation; format-only may be changed=true material=false. PRICE: $0.005 USDC (Base Sepolia) via x402 per successful check. TESTNET/STAGING. Next (suggestion only, never auto-invoked): store observation_id; if material → web_fetch_clean / web_extract_json.
naun_capabilitiesWHEN: Discover tools, prices, networks, limits before paying. OUTPUT: Catalog object (tools + limitations + prices). LIMITATION: Read-only staging catalog; never invents mainnet/commercial. PRICE: Free — never charges. Next (suggestion only): pick paid tool matching job; confirm Base Sepolia USDC.
naun_healthWHEN: Liveness / health before paid work or diagnosing connectivity. OUTPUT: Health JSON (environment, commercial_revenue_eligible=false, prices). LIMITATION: Liveness only — not a paid SKU; does not prove a URL is fetchable. PRICE: Free — never charges. Next (suggestion only): naun_capabilities then appropriate paid tool.